Happy Horse 1.0 is now on ModelsLab

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

Veo 2Cinematic Videos Instant

Try Veo 2API Documentation

Master Veo 2 Generation

Text-to-Video

Veo 2 API Core

Generate 5-8 second 720p videos from text prompts with physics-aware motion.

Image-to-Video

Veo 2 Extension

Animate images up to 20MB into videos using Google/Veo 2 endpoint.

Cinematic Controls

Precise Prompting

Specify camera angles, lenses, and effects for realistic outputs.

Endpoints

Multiple endpoints, one model

Veo 2 is available through 2 specialized endpoints. Choose the one that fits your workflow.

Google/Veo 2veo2Veo 2 Image to Videoveo2Image2video

Examples

See what Veo 2 can create

Copy any prompt below and try it yourself in the playground.

Ice Cave Journey

“Cinematic tracking shot through magical ice cave, massive crystalline icicles glowing blue, camera moves between formations with water drips and rainbow refractions, misty air, dreamy quality.”

Desert Drive

“Tracking drone view of red convertible driving in 1970s Palm Springs, warm sunlight, long shadows, 16:9 widescreen, smooth motion.”

Urban Timelapse

“Timelapse of city skyline at dusk, lights flickering on, clouds drifting, 16:9 aspect, shallow depth of field, realistic physics.”

Ocean Waves

“Low-angle shot of waves crashing on rocky shore, foam spraying, seagulls flying, natural motion, 9:16 portrait, 24 FPS.”

For Developers

A few lines of code.
Videos. Few Lines.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
API Documentation 
import requests


response = requests.post(
    "https://modelslab.com/api/v7/video-fusion/text-to-video",
    json={
  "key": "YOUR_API_KEY",
  "prompt": "A hooded wizard stands on a stormy mountainside. The camera slowly zooms in as he raises his glowing green hand of energy and places it firmly on his chest. The green energy rapidly pulses and spreads through his entire body like veins of lightning, illuminating his form. His eyes ignite with the same energy as powerful wind whips through his cloak and hood, making them billow dramatically. Debris lifts from the ground and swirls around him. He clenches his fists and lifts his head, clearly empowered. Magical sparks and glowing particles float in the air. High quality, cinematic, ultra realistic, 4k, dramatic lighting, cool special effects, dynamic wind motion, flowing fabric, immersive atmosphere.",
  "portrait": ""
}
)
print(response.json())

FAQ

Common questions about Veo 2

Read the docs

Veo 2 is Google's AI for high-quality video generation up to 720p. It supports 5-8 second clips with realistic physics. Access via Veo 2 API.

Input text or images to generate MP4 videos at 24 FPS. Supports 16:9 and 9:16 ratios. Outputs up to 4 videos per prompt.

Current output is 720p. Model supports up to 4K in future. Input images max 20MB at 720p.

Yes, via Google/Veo 2 endpoint. Animate static images into 5-8s clips. Matches text prompt styles.

Use specific camera terms like 18mm lens or tracking shots. Include aspect ratios and effects. Experiment for cinematic results.

Yes for short clips and prototypes. Limits: 8s max, 720p now. Scales via endpoints.

Ready to create?

Start generating with Veo 2 on ModelsLab.

Try Veo 2API Documentation